Abstract
Natural Language Processing (NLP) is the sub-field of Artificial Intelligence that represents and analyses human language automatically. NLP has been employed in many applications, such as information retrieval, information processing and automated answer ranking. Semantic analysis focuses on understanding the meaning of text. Among other proposed approaches, Latent Semantic Analysis (LSA) is a widely used corpus-based approach that evaluates similarity of text based on the semantic relations among words. LSA has been applied successfully in diverse language systems for calculating the semantic similarity of texts. LSA ignores the structure of sentences, i.e., it suffers from a syntactic blindness problem. LSA fails to distinguish between sentences that contain semantically similar words but have opposite meanings. Disregarding sentence structure, LSA cannot differentiate between a sentence and a list of keywords. If the list and the sentence contain similar words, comparing them using LSA would lead to a high similarity score. In this paper, we propose xLSA, an extension of LSA that focuses on the syntactic structure of sentences to overcome the syntactic blindness problem of the original LSA approach. xLSA was tested on sentence pairs that contain similar words but have significantly different meaning. Our results showed that xLSA alleviates the syntactic blindness problem, providing more realistic semantic similarity scores.
Highlights
Natural Language Processing (NLP) is the sub-field of Artificial In telligence that focusses on understanding and generating natural lan guage by machines (Khurana et al, 2017)
Simple Latent Semantic Analysis (LSA) gives a semantic similarity score of 100% to all the sentences that have similar words, irrespectively of the effect they have on the meaning of a sentence. xLSA has been designed to calculate se mantic similarity based on similar words, and on the syn tactic structure of the sentences and the positioning of words in them
This allows xLSA to distinguish between sentences that are semantically related on the surface level, i.e., based on the words that they contain, but convey completely different meaning
Summary
Natural Language Processing (NLP) is the sub-field of Artificial In telligence that focusses on understanding and generating natural lan guage by machines (Khurana et al, 2017). Simple string-based metrics only apply in cases of exact word matching They do not consider inflection, synonyms and sentence structure. Latent Semantic Analysis (LSA) is one such technique, allowing to compute the “semantic” overlap between text snippets. LSA considers that words with similar meaning will occur in similar contexts It has been used successfully in a diverse range of NLP applications (Landauer, 2002; Vrana et al, 2018; Wegba et al, 2018; Jirasatjanukul et al, 2019). It has been extensively used as an approximation to human semantic knowledge and verbal intelligence in the context of Intelligent Tutoring Systems (ITS). Hyperspace Analogue to Language (HAL), Pointwise Mutual Information – Information Retrieval (PMI-IR) and Latent Semantic Analysis are some of the most popular corpus-based similarity approaches
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
